Multilayer feedforward networks are universal approximators
Neural Networks
Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Neural networks and the bias/variance dilemma
Neural Computation
Prolepsis on the problem of Trojan-horse based integrity attacks (position paper)
Proceedings of the 1998 workshop on New security paradigms
Advances in Feedforward Neural Networks: Demystifying Knowledge Acquiring Black Boxes
IEEE Transactions on Knowledge and Data Engineering
Analysis of Neural Cryptography
ASIACRYPT '02 Proceedings of the 8th International Conference on the Theory and Application of Cryptology and Information Security: Advances in Cryptology
A Toolkit for Detecting and Analyzing Malicious Software
ACSAC '02 Proceedings of the 18th Annual Computer Security Applications Conference
Neural Networks in Business Forecasting
Neural Networks in Business Forecasting
A network intrusion detection system based on the artificial neural networks
InfoSecu '04 Proceedings of the 3rd international conference on Information security
A Case-Based Explanation System for Black-Box Systems
Artificial Intelligence Review
Anomaly Detection Based Intrusion Detection
ITNG '06 Proceedings of the Third International Conference on Information Technology: New Generations
Proceedings of the 1st workshop on Architectural and system support for improving software dependability
Neural Networks in Healthcare: Potential and Challenges
Neural Networks in Healthcare: Potential and Challenges
Neural Networks in Finance: Gaining Predictive Edge in the Market (Academic Press Advanced Finance Series)
Encrypting Algorithm Based on RBF Neural Network
ICNC '07 Proceedings of the Third International Conference on Natural Computation - Volume 01
A Classification of Viruses Through Recursion Theorems
CiE '07 Proceedings of the 3rd conference on Computability in Europe: Computation and Logic in the Real World
Study on Information Hiding Algorithm Based on RBF and LSB
ICNC '08 Proceedings of the 2008 Fourth International Conference on Natural Computation - Volume 05
CMC '09 Proceedings of the 2009 WRI International Conference on Communications and Mobile Computing - Volume 03
Network Intrusion Detection Method Based on Improved Simulated Annealing Neural Network
ICMTMA '09 Proceedings of the 2009 International Conference on Measuring Technology and Mechatronics Automation - Volume 03
A framework for quantitative security analysis of machine learning
Proceedings of the 2nd ACM workshop on Security and artificial intelligence
Adversarial Knowledge Discovery
IEEE Intelligent Systems
Classification Algorithms of Trojan Horse Detection Based on Behavior
MINES '09 Proceedings of the 2009 International Conference on Multimedia Information Networking and Security - Volume 02
Dynamic Attack Tree and Its Applications on Trojan Horse Detection
MMIT '10 Proceedings of the 2010 Second International Conference on MultiMedia and Information Technology - Volume 01
Intrusion Detection and Attack Classification Using Feed-Forward Neural Network
ICCNT '10 Proceedings of the 2010 Second International Conference on Computer and Network Technology
The security of machine learning
Machine Learning
A Clustering Algorithm Use SOM and K-Means in Intrusion Detection
ICEE '10 Proceedings of the 2010 International Conference on E-Business and E-Government
Automated remote repair for mobile malware
Proceedings of the 27th Annual Computer Security Applications Conference
Toward an abstract computer virology
ICTAC'05 Proceedings of the Second international conference on Theoretical Aspects of Computing
Intrusion detection techniques and approaches
Computer Communications
Neural-network feature selector
IEEE Transactions on Neural Networks
Perceptron-based learning algorithms
IEEE Transactions on Neural Networks
ICEC'07 Proceedings of the 6th international conference on Entertainment Computing
Hi-index | 0.00 |
This paper presents a proof of concept of a neural network Trojan. The neural network Trojan consists of a neural network that has been trained with a compromised dataset and modified code. The Trojan implementation is carried out by insertion of a malicious payload encoded into the weights alongside with the data of the intended application. The neural Trojan is specifically designed so that when a specific entry is fed into the trained neural network, it triggers the interpretation of the data as payload. The paper presents a background on which this attack is based and provides the assumptions that make the attack possible. Two embodiments of the attack are presented consisting of a basic backpropagation network and a Neural Network Trojan with Sequence Processing Connections NNTSPC. The two alternatives are used depending on the underlying circumstances on which the compromise is launched. Experimental results are carried out with synthetic as well as a chosen existing binary payload. Practical issues of the attack are also discussed, as well as a discussion on detection techniques.